Related papers: VisCRA: A Visual Chain Reasoning Attack for Jailbr…

The rapid development of Large Language Models (LLMs) has brought impressive advancements across various tasks. However, despite these achievements, LLMs still pose inherent safety risks, especially in the context of jailbreak attacks. Most…

Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of the visual modality. Even when text prompts contain explicit harmful intent, adding an image can substantially increase jailbreak success…

Large Reasoning Models (LRMs) have recently extended their powerful reasoning capabilities to safety checks-using chain-of-thought reasoning to decide whether a request should be answered. While this new approach offers a promising route…

The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol…

Emerging large reasoning models (LRMs), such as DeepSeek-R1 models, leverage long chain-of-thought (CoT) reasoning to generate structured intermediate steps, enhancing their reasoning capabilities. However, long CoT does not inherently…

The rapid development of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has exposed vulnerabilities to various adversarial attacks. This paper provides a comprehensive overview of jailbreaking research targeting…

Multimodal large language models (MLLMs) enable powerful cross-modal reasoning capabilities. However, the expanded input space introduces new attack surfaces. Previous jailbreak attacks often inject malicious instructions from text into…

With the rapid advancements in Multimodal Large Language Models (MLLMs), securing these models against malicious inputs while aligning them with human values has emerged as a critical challenge. In this paper, we investigate an important…

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same…

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in cross-modal understanding, but remain vulnerable to adversarial attacks through visual inputs despite robust textual safety mechanisms. These…

Multimodal Large Reasoning Models (MLRMs) have achieved remarkable strides in visual reasoning through test time compute scaling, yet long chain reasoning remains prone to hallucinations. We identify a concerning phenomenon termed the…

Large language models (LLMs) have gained widespread recognition for their superior comprehension and have been deployed across numerous domains. Building on Chain-of-Thought (CoT) ideology, Large Reasoning models (LRMs) further exhibit…

Large Vision-Language Models (VLMs) have achieved remarkable performance across a wide range of tasks. However, their deployment in safety-critical domains poses significant challenges. Existing safety fine-tuning methods, which focus on…

Jailbreaking -- bypassing built-in safety mechanisms in AI models -- has traditionally required complex technical procedures or specialized human expertise. In this study, we show that the persuasive capabilities of large reasoning models…

Despite their superb capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks. While recent jailbreaks have achieved notable progress, their effectiveness and efficiency can still be improved. In…

Vision-Language-Action (VLA) models with integrated reasoning have been proposed for end-to-end autonomous driving, assuming a tight coupling between reasoning and trajectory generation. However, the robustness of such systems under…

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit textual or visual triggers to bypass safety guardrails. Recent…

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…